Name: ax-go-agent-rlm
Rating: 68 (1 reviews)
Author: ax-llm

ax-go-agent-rlm

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, well-organized reference body with genuine Go code and useful guardrails, held back mainly by an API-name inconsistency between the Core Pattern (`ax.`) and the API surface (`axllm.`), plus an undefined `llm` variable in the snippet.

Suggestions

Resolve the package-qualifier inconsistency: the Core Pattern uses `ax.NewAgent`/`ax.Value` while Relevant API Surface lists `axllm.NewAgent`/`axllm.AxAgent` — pick the correct prefix so the snippet is copy-paste ready.

Complete the Core Pattern snippet with the import block and construction of `llm` (e.g., via a scripted no-key transport) so it runs as written.

Add a short ordered sequence for wiring a runtime (choose transport → construct agent → forward → inspect result) to make the implicit guardrail flow an explicit workflow.

Dimension	Reasoning	Score
Conciseness	The ~40-line body is lean and factual with no padding and no explanations of concepts Claude already knows; every section (Package Facts, Relevant API Surface, Guardrails) earns its tokens. It cleanly matches the 'lean and efficient' anchor.	5 / 5
Actionability	The Core Pattern is real Go code backed by concrete API names and example-first guardrails, making the guidance mostly executable. It falls short of anchor 5 because `llm` is undefined with no imports shown, and the snippet's `ax.NewAgent`/`ax.Value` prefix contradicts the API surface's `axllm.NewAgent`/`axllm.AxAgent`.	4 / 5
Workflow Clarity	Guardrails encode a usable decision flow ('Start from package examples', 'Use no-key examples for deterministic local checks', 'Use provider-api examples only when the user explicitly has provider credentials'), but steps are not sequenced and no validation checkpoints are given for wiring a runtime. Above anchor 3 because the guidance is unambiguous for this single-purpose skill; below anchor 5 because the ordering is implicit.	4 / 5
Progressive Disclosure	Under 50 lines with well-organized sections (When To Use, Package Facts, Core Pattern, Relevant API Surface, Guardrails) and clearly signaled one-level-deep pointers to package artifacts (API.md, axir-api.json, examples/) that live in the target package rather than the skill bundle. Per the simple-skill guidance, this earns a 5 with no external skill references required.	5 / 5
	Total	18 / 20 Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with an explicit 'Use when' trigger, an exact package identifier, and several concrete capability areas. The main room for improvement is separating the 'what' from the 'when' and adding a few more natural synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability areas — 'RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles' — rather than vague language. It is not anchor 5 because the items are topic areas rather than explicit action verbs, so what is done with them is only implied.	4 / 5
Completeness	Explicitly answers 'when' via 'Use when writing Go code with github.com/ax-llm/ax/packages/go for...' with concrete triggers, and the 'what' (writing Go code for the listed areas) is present but fused into the when-clause rather than stated as a distinct capability sentence. Not anchor 5 because the 'what' could be more explicit; not anchor 3 because 'when' is explicit rather than merely implied.	4 / 5
Trigger Term Quality	Includes exact natural terms a user of this package would say ('Go code', 'RLM executor loops', 'AxCodeRuntime', 'runtime profiles') plus the full package path. Missing common variations like 'Golang', 'AxCodeSession', or 'Goja', so it falls short of the comprehensive-synonym anchor 5 but sits well above anchor 3.	4 / 5
Distinctiveness Conflict Risk	The exact package path 'github.com/ax-llm/ax/packages/go' and niche API names (AxCodeRuntime, ProcessCodeRuntime, RLM) create a clear, narrowly scoped trigger with minimal conflict risk against any other skill.	5 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: ax-llm/ax
Path: packages/go/skills/ax-go-agent-rlm/SKILL.md
Commit: 3f630a0

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.